New RunLLM response generated: >>>*# Question* Hi there! We've been encountering an unusual issue where occasionally creating executions with

overwrite_cache=True

doesn't actually run new tasks and overwrite the cache as expected - instead Flyte tries to recover previous outputs and typically hits an

OutputsNotFound

error due to some mismatch between the previous and new run. We're using FlyteRemote to programatically create these executions as a way of relaunching previously failed executions - we do this instead of clicking 'relaunch' on the Flyte UI so that we can customise the execution name as well as relaunch executions in bulk. Has anyone else had this issue, and is there perhaps something we're missing about our relaunching setup? I'll add a code snippet to the thread... # Answer This issue might be related to how the

overwrite_cache

flag is being used. According to the Flyte documentation, the

overwrite_cache

flag is intended to invalidate the cache and force re-execution of the task. However, if the task's inputs or configuration haven't changed, Flyte might still attempt to use the cached outputs, leading to the

OutputsNotFound

error if those outputs are missing or mismatched. To troubleshoot, ensure that the

overwrite_cache

parameter is correctly set in the

FlyteRemote.execute

method. Additionally, verify that the task inputs or configurations are indeed different from the previous execution to ensure that Flyte recognizes the need to re-run the task. If the issue persists, it might be beneficial to check the Flyte logs for any additional error messages or warnings that could provide more context. Would you like more detailed guidance on setting up the

FlyteRemote.execute

method or any other aspect of your relaunching setup? Sources: - Flyte documentation Slack Link https://flyte.slack.com/archives/CP2HDHKE1/p1732187690.142099 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.